we gave our AI an eye for detail. 👀 Meet WeVisOne-VL, an open-source 2B/4B model from our Weixin Vision team. It finds and counts objects, reads text, and makes precise masks and cutouts—no separate SAM needed. Not in the image? "None."

Your AI agent just got teammates. And a schedule. WeKnora v0.9.0 brings multi-agent collaboration and scheduled tasks to our open-source AI knowledge platform. 🤝 Share the workload: break complex tasks into independent subtasks, delegate them to agents and bring the results together. ⏰ Put tasks on a schedule: set them to run once or repeat automatically, with execution history and results to review. Explore the release on GitHub:

Think you know China travel? 😏 From Oct 1–5, these were the 10 most-visited Mini Programs for tourist attractions during Golden Week. How many have you checked off? And if China’s next on your list… apparently your itinerary needs WeChat too. 😌

So yeah… this is what we were teasing last night. TenPayGo for the trip. And yes, WeChat supports international cards and e-wallets too. We’ve had that covered for a while — but good to know we can still surprise you. 👀 If the trip somehow turns into new friends, group chats and “when are you coming back?” That part’s still our department.

Search it. See it. Keep reasoning with it. 👀 That last part is harder than it sounds. In many search-agent setups, images retrieved along the way are not preserved in the model’s later context. As a result, a seemingly multimodal search trajectory can gradually collapse back into text-only reasoning. WeAgent-MMSearch, developed by the Weixin AI team at Tencent, is designed to keep visual evidence in the loop. With a persistent multimodal state, retrieved images remain accessible throughout the search trajectory. The agent can revisit them, cross-check visual evidence across turns, perform reverse-image searches, and reason over the retrieved images directly in subsequent reasoning and tool calls — rather than reducing everything to text. With agentic SFT followed by Failure-Aware GSPO, WeAgent-MMSearch reaches an average score of 55.97 across 8 benchmarks, up 19.22 points from baseline. We also introduce VisTarget-Bench, a human-verified benchmark of 150 tasks designed to disentangle two failure modes that standard evaluation often conflates: failing to retrieve the right visual evidence, and failing to answer correctly even after that evidence has been retrieved. Each task is paired with a held-out target image, allowing us to separately measure whether the agent retrieves the intended evidence and whether it can answer correctly once that evidence has been found. For multimodal search, finding the evidence is only the beginning. More on WeAgent-MMSearch:

Us: “Can you make this email sound warmer?” Students: build Mini Programs with AI Humbling. This year’s Weixin Mini Program Global Innovation Challenge is now on in Hong Kong, with the Hong Kong Education Bureau joining as a co-organizer for the first time. Yeah, the kids are busy building.

Put your team’s knowledge to work. Developed by Tencent’s Weixin team, WeKnora is an open-source, LLM-powered knowledge framework built for enterprise-grade document understanding, semantic retrieval, and autonomous reasoning. Build assistants that find answers in your docs, show their sources and use skills to create files you can preview and download. Keep useful context across chats with opt-in long-term memory. You approve suggested memories before they’re used. Self-host it and run skills in a sandbox with network limits you set. Explore WeKnora: Have a project in mind? Join our community to share ideas and build with us: